Downloads · 30 days
24
3% of all-time downloads
tiny-random-vit-finetuned-eurosat
keithanpai/tiny-random-vit-finetuned-eurosat
tiny-random-vit-finetuned-eurosat is a image classification model from keithanpai. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
832
Public
Repo size
802 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin199 KB · 92%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- vit
- Access
- Public
- Created
- Aug 1, 2022
- Updated
- Aug 1, 2022
- SHA
- 0815a744
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
tiny-random-vit-finetuned-eurosat
This model is a fine-tuned version of hf-internal-testing/tiny-random-vit on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0488
- Accuracy: 0.6647
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1192 | 0.99 | 70 | 1.0867 | 0.6627 |
| 1.067 | 1.99 | 140 | 1.0563 | 0.6657 |
| 0.9719 | 2.99 | 210 | 1.0488 | 0.6647 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- Created
- Aug 1, 2022
- Updated
- Aug 1, 2022